linux-stable/net/bridge/br_vlan_tunnel.c
NeilBrown 8f0db01800 rhashtable: use bit_spin_locks to protect hash bucket.
This patch changes rhashtables to use a bit_spin_lock on BIT(1) of the
bucket pointer to lock the hash chain for that bucket.

The benefits of a bit spin_lock are:
 - no need to allocate a separate array of locks.
 - no need to have a configuration option to guide the
   choice of the size of this array
 - locking cost is often a single test-and-set in a cache line
   that will have to be loaded anyway.  When inserting at, or removing
   from, the head of the chain, the unlock is free - writing the new
   address in the bucket head implicitly clears the lock bit.
   For __rhashtable_insert_fast() we ensure this always happens
   when adding a new key.
 - even when lockings costs 2 updates (lock and unlock), they are
   in a cacheline that needs to be read anyway.

The cost of using a bit spin_lock is a little bit of code complexity,
which I think is quite manageable.

Bit spin_locks are sometimes inappropriate because they are not fair -
if multiple CPUs repeatedly contend of the same lock, one CPU can
easily be starved.  This is not a credible situation with rhashtable.
Multiple CPUs may want to repeatedly add or remove objects, but they
will typically do so at different buckets, so they will attempt to
acquire different locks.

As we have more bit-locks than we previously had spinlocks (by at
least a factor of two) we can expect slightly less contention to
go with the slightly better cache behavior and reduced memory
consumption.

To enhance type checking, a new struct is introduced to represent the
  pointer plus lock-bit
that is stored in the bucket-table.  This is "struct rhash_lock_head"
and is empty.  A pointer to this needs to be cast to either an
unsigned lock, or a "struct rhash_head *" to be useful.
Variables of this type are most often called "bkt".

Previously "pprev" would sometimes point to a bucket, and sometimes a
->next pointer in an rhash_head.  As these are now different types,
pprev is NULL when it would have pointed to the bucket. In that case,
'blk' is used, together with correct locking protocol.

Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-04-07 19:12:12 -07:00

204 lines
4.6 KiB
C

/*
* Bridge per vlan tunnel port dst_metadata handling code
*
* Authors:
* Roopa Prabhu <roopa@cumulusnetworks.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <net/switchdev.h>
#include <net/dst_metadata.h>
#include "br_private.h"
#include "br_private_tunnel.h"
static inline int br_vlan_tunid_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
const struct net_bridge_vlan *vle = ptr;
__be64 tunid = *(__be64 *)arg->key;
return vle->tinfo.tunnel_id != tunid;
}
static const struct rhashtable_params br_vlan_tunnel_rht_params = {
.head_offset = offsetof(struct net_bridge_vlan, tnode),
.key_offset = offsetof(struct net_bridge_vlan, tinfo.tunnel_id),
.key_len = sizeof(__be64),
.nelem_hint = 3,
.obj_cmpfn = br_vlan_tunid_cmp,
.automatic_shrinking = true,
};
static struct net_bridge_vlan *br_vlan_tunnel_lookup(struct rhashtable *tbl,
u64 tunnel_id)
{
return rhashtable_lookup_fast(tbl, &tunnel_id,
br_vlan_tunnel_rht_params);
}
void vlan_tunnel_info_del(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan)
{
if (!vlan->tinfo.tunnel_dst)
return;
rhashtable_remove_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
vlan->tinfo.tunnel_id = 0;
dst_release(&vlan->tinfo.tunnel_dst->dst);
vlan->tinfo.tunnel_dst = NULL;
}
static int __vlan_tunnel_info_add(struct net_bridge_vlan_group *vg,
struct net_bridge_vlan *vlan, u32 tun_id)
{
struct metadata_dst *metadata = NULL;
__be64 key = key32_to_tunnel_id(cpu_to_be32(tun_id));
int err;
if (vlan->tinfo.tunnel_dst)
return -EEXIST;
metadata = __ip_tun_set_dst(0, 0, 0, 0, 0, TUNNEL_KEY,
key, 0);
if (!metadata)
return -EINVAL;
metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_BRIDGE;
vlan->tinfo.tunnel_dst = metadata;
vlan->tinfo.tunnel_id = key;
err = rhashtable_lookup_insert_fast(&vg->tunnel_hash, &vlan->tnode,
br_vlan_tunnel_rht_params);
if (err)
goto out;
return 0;
out:
dst_release(&vlan->tinfo.tunnel_dst->dst);
vlan->tinfo.tunnel_dst = NULL;
vlan->tinfo.tunnel_id = 0;
return err;
}
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
*/
int nbp_vlan_tunnel_info_add(struct net_bridge_port *port, u16 vid, u32 tun_id)
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *vlan;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
vlan = br_vlan_find(vg, vid);
if (!vlan)
return -EINVAL;
return __vlan_tunnel_info_add(vg, vlan, tun_id);
}
/* Must be protected by RTNL.
* Must be called with vid in range from 1 to 4094 inclusive.
*/
int nbp_vlan_tunnel_info_delete(struct net_bridge_port *port, u16 vid)
{
struct net_bridge_vlan_group *vg;
struct net_bridge_vlan *v;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
v = br_vlan_find(vg, vid);
if (!v)
return -ENOENT;
vlan_tunnel_info_del(vg, v);
return 0;
}
static void __vlan_tunnel_info_flush(struct net_bridge_vlan_group *vg)
{
struct net_bridge_vlan *vlan, *tmp;
list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist)
vlan_tunnel_info_del(vg, vlan);
}
void nbp_vlan_tunnel_info_flush(struct net_bridge_port *port)
{
struct net_bridge_vlan_group *vg;
ASSERT_RTNL();
vg = nbp_vlan_group(port);
__vlan_tunnel_info_flush(vg);
}
int vlan_tunnel_init(struct net_bridge_vlan_group *vg)
{
return rhashtable_init(&vg->tunnel_hash, &br_vlan_tunnel_rht_params);
}
void vlan_tunnel_deinit(struct net_bridge_vlan_group *vg)
{
rhashtable_destroy(&vg->tunnel_hash);
}
int br_handle_ingress_vlan_tunnel(struct sk_buff *skb,
struct net_bridge_port *p,
struct net_bridge_vlan_group *vg)
{
struct ip_tunnel_info *tinfo = skb_tunnel_info(skb);
struct net_bridge_vlan *vlan;
if (!vg || !tinfo)
return 0;
/* if already tagged, ignore */
if (skb_vlan_tagged(skb))
return 0;
/* lookup vid, given tunnel id */
vlan = br_vlan_tunnel_lookup(&vg->tunnel_hash, tinfo->key.tun_id);
if (!vlan)
return 0;
skb_dst_drop(skb);
__vlan_hwaccel_put_tag(skb, p->br->vlan_proto, vlan->vid);
return 0;
}
int br_handle_egress_vlan_tunnel(struct sk_buff *skb,
struct net_bridge_vlan *vlan)
{
int err;
if (!vlan || !vlan->tinfo.tunnel_id)
return 0;
if (unlikely(!skb_vlan_tag_present(skb)))
return 0;
skb_dst_drop(skb);
err = skb_vlan_pop(skb);
if (err)
return err;
skb_dst_set(skb, dst_clone(&vlan->tinfo.tunnel_dst->dst));
return 0;
}